© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 105390
    Prev
    Next
    INDEX
    Explanations

    -analysis

    np_max-act · gemini-2.0-flash

    medical-related terms and phrases pertaining to cancer and its treatment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guru
    -0.07
    (fake
    -0.07
    QualifiedName
    -0.06
    ${
    -0.06
     Save
    -0.06
    取
    -0.06
    .tabs
    -0.06
     따라
    -0.06
    olved
    -0.06
    _FIELDS
    -0.06
    POSITIVE LOGITS
    �
    0.07
    486
    0.07
    926
    0.07
     yytype
    0.07
    OCUS
    0.07
    Attend
    0.06
     arası
    0.06
    368
    0.06
    .badlogic
    0.06
    055
    0.06
    Activations Density 0.003%

    No Known Activations